摘要
现代战场环境日益复杂,随着空中机载装备技术的升级,海量多源异构传感器数据不可避免地出现信息不一致、不完备问题.传统面向机载多源传感器量测数据的融合处理方法忽略传感特征间的相关性,单依赖物理传感器的数据驱动形成封闭识别系统.考虑到专家认知、领域参数、属性规则等知识能以专家经验、规则约束等辅助认知形式在目标综合识别的模型构建、推理识别等环节起到指导作用,本文提出一种知识辅助的空中目标类型综合识别方法,利用上述知识,首先构建典型空中目标特征军事作战知识图谱,提取关键特征参数、识别规则阈值等建立目标辨识框架关联关系模型;然后在特征级识别、决策级识别层分别构建数据基本信任指派与证据冲突可信度;此外,针对证据出现高冲突情况制定时域融合规则,引入历史数据重构调整数据时序融合权重因子;最后在静态推理与动态融合下分层实现异构多源传感器的置信类型综合识别.本文在典型空中目标类型识别任务下识别准确率优于现有算法,验证了所提方法的有效性.
With the increasing complexity of modern battlefield environment and the upgrading of aviation equip⁃ment technology,massive multi-source heterogeneous sensor data inevitably appear inconsistent and incomplete problems.Traditional multi-sensor fusion method ignores sensor features correlation,and forms a closed data-driven recognition sys⁃tem of sensors.Whereas expert cognition,domain experience,attribute rules and other knowledge can instruct model con⁃struction and inference recognition of comprehensive target recognition in the form of expert experience,rule constraints and so on,this paper presents a method of knowledge assisted integrated identification of aerial targets.First of all,a mili⁃tary combat knowledge map of typical aerial target features is constructed,and key feature parameters are extracted to estab⁃lish a target identification framework model.Then data basic trust assignment and evidence conflict credibility are construct⁃ed at recognition and decision recognition level respectively.Besides,time-domain fusion rules for high-conflict evidence is formulated to adjust timing fusion weights by using historical data.Finally,type recognition of multi-sensor is hierarchical⁃ly realized through static reasoning and dynamic fusion.This study recognition accuracy is better than the existing algo⁃rithms in typical aerial target recognition tasks,demonstrating the effectiveness of the proposed algorithm.
作者
崔艺涵
梁彦
宋欠欠
张会霞
王帆
CUI Yi-han;LIANG Yan;SONG Qian-qian;ZHANG Hui-xia;WANG Fan(School of Automation,Northwestern Polytechnical University,Xi'an,Shaanxi 710129,China;Department of Optoelectronic Systems,The 27th Research Institute of China Electronics Technology Group Corporation,Zhengzhou,Henan 450047,China)
出处
《电子学报》
EI
CAS
CSCD
北大核心
2024年第9期2961-2970,共10页
Acta Electronica Sinica
基金
国家自然科学基金(No.61873205)。
关键词
目标综合识别
时序融合
空中目标
知识辅助
置信规则分类
target identification fusion
sequential fusion
aerial target
multiple knowledge
belief rule-based classi⁃fication key word
